SAS Viya — Claude Code MCP server: what it does, how to install
Executes SAS code, orchestrates AutoML pipelines, and queries SAS Viya APIs directly from your AI workspace.
claude mcp add --env VIYA_ENDPOINT=<VIYA_ENDPOINT> --env SSL_VERIFY=<SSL_VERIFY> --env CLIENT_ID=<CLIENT_ID> --env COMPUTE_CONTEXT_NAME=<COMPUTE_CONTEXT_NAME> --env MCP_TIERS=<MCP_TIERS> --transport stdio sas-viya -- docker run -i --rm -e VIYA_ENDPOINT -e SSL_VERIFY -e CLIENT_ID -e COMPUTE_CONTEXT_NAME -e MCP_TIERS ghcr.io/sassoftware/sas-mcp-server:1.19.0What SAS Viya does
The server connects your LLM client to a SAS Viya analytics deployment. It provides 115 tools split across 11 selectable tiers, covering tasks from basic code execution to model scoring. Assistants can inspect data, fetch execution logs, and monitor CAS compute sessions inside the chat.
Several deployment patterns are supported out of the box: a stdio process, a standalone HTTP service listening on port 8134, or a Docker container. Authentication handles OAuth 2.0 PKCE in the browser, though scripts can also supply an existing bearer token directly.
A functional SAS Viya environment with compute service access is strictly required before configuring the client. Running natively without Docker calls for Python 3.12+ and uv 0.8+.
What it helps with
- Run SAS scripts and review compute session logs
- Trigger AutoML model training and evaluate metrics
- Inspect analytical tables and manage CAS sessions
- Access SAS Viya endpoints using OAuth 2.0 PKCE authentication
Example prompts for the agent
- Execute this SAS code block in the default compute context and return the log
- Start an AutoML training run on the customer metrics dataset
- Check active CAS sessions and list available data tables
How to install SAS Viya
Platform CLI
claude mcp add --env VIYA_ENDPOINT=<VIYA_ENDPOINT> --env SSL_VERIFY=<SSL_VERIFY> --env CLIENT_ID=<CLIENT_ID> --env COMPUTE_CONTEXT_NAME=<COMPUTE_CONTEXT_NAME> --env MCP_TIERS=<MCP_TIERS> --transport stdio sas-viya -- docker run -i --rm -e VIYA_ENDPOINT -e SSL_VERIFY -e CLIENT_ID -e COMPUTE_CONTEXT_NAME -e MCP_TIERS ghcr.io/sassoftware/sas-mcp-server:1.19.0Replace <…> with your own values. 4 more environment variables are in the server README
Platform CLI
codex mcp add sas-viya --env VIYA_ENDPOINT=<VIYA_ENDPOINT> --env SSL_VERIFY=<SSL_VERIFY> --env CLIENT_ID=<CLIENT_ID> --env COMPUTE_CONTEXT_NAME=<COMPUTE_CONTEXT_NAME> --env MCP_TIERS=<MCP_TIERS> -- docker run -i --rm -e VIYA_ENDPOINT -e SSL_VERIFY -e CLIENT_ID -e COMPUTE_CONTEXT_NAME -e MCP_TIERS ghcr.io/sassoftware/sas-mcp-server:1.19.0Replace <…> with your own values. 4 more environment variables are in the server README
Config file
{
"mcpServers": {
"sas-viya": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"VIYA_ENDPOINT",
"-e",
"SSL_VERIFY",
"-e",
"CLIENT_ID",
"-e",
"COMPUTE_CONTEXT_NAME",
"-e",
"MCP_TIERS",
"ghcr.io/sassoftware/sas-mcp-server:1.19.0"
],
"env": {
"VIYA_ENDPOINT": "<VIYA_ENDPOINT>",
"SSL_VERIFY": "<SSL_VERIFY>",
"CLIENT_ID": "<CLIENT_ID>",
"COMPUTE_CONTEXT_NAME": "<COMPUTE_CONTEXT_NAME>",
"MCP_TIERS": "<MCP_TIERS>"
}
}
}
}Replace <…> with your own values. 4 more environment variables are in the server README
Config file
{
"servers": {
"sas-viya": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"VIYA_ENDPOINT",
"-e",
"SSL_VERIFY",
"-e",
"CLIENT_ID",
"-e",
"COMPUTE_CONTEXT_NAME",
"-e",
"MCP_TIERS",
"ghcr.io/sassoftware/sas-mcp-server:1.19.0"
],
"env": {
"VIYA_ENDPOINT": "<VIYA_ENDPOINT>",
"SSL_VERIFY": "<SSL_VERIFY>",
"CLIENT_ID": "<CLIENT_ID>",
"COMPUTE_CONTEXT_NAME": "<COMPUTE_CONTEXT_NAME>",
"MCP_TIERS": "<MCP_TIERS>"
}
}
}
}Replace <…> with your own values. 4 more environment variables are in the server README
Platform CLI
gemini mcp add -e VIYA_ENDPOINT=<VIYA_ENDPOINT> -e SSL_VERIFY=<SSL_VERIFY> -e CLIENT_ID=<CLIENT_ID> -e COMPUTE_CONTEXT_NAME=<COMPUTE_CONTEXT_NAME> -e MCP_TIERS=<MCP_TIERS> sas-viya docker run -i --rm -e VIYA_ENDPOINT -e SSL_VERIFY -e CLIENT_ID -e COMPUTE_CONTEXT_NAME -e MCP_TIERS ghcr.io/sassoftware/sas-mcp-server:1.19.0Replace <…> with your own values. 4 more environment variables are in the server README
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about SAS Viya
How to install SAS Viya in Claude Code?
Run `claude mcp add --env VIYA_ENDPOINT=<VIYA_ENDPOINT> --env SSL_VERIFY=<SSL_VERIFY> --env CLIENT_ID=<CLIENT_ID> --env COMPUTE_CONTEXT_NAME=<COMPUTE_CONTEXT_NAME> --env MCP_TIERS=<MCP_TIERS> --transport stdio sas-viya -- docker run -i --rm -e VIYA_ENDPOINT -e SSL_VERIFY -e CLIENT_ID -e COMPUTE_CONTEXT_NAME -e MCP_TIERS ghcr.io/sassoftware/sas-mcp-server:1.19.0`. Replace bracketed placeholders with your actual Viya connection details.
What does the SAS Viya MCP server do?
It gives AI assistants 115 tools to execute SAS programs, run AutoML experiments, and interact with Viya CAS and compute APIs.
How is authentication handled?
It relies on OAuth 2.0 with PKCE via browser prompt. For stdio setups, you can pre-authenticate using uv run sas-mcp-login or the official sas-viya auth loginCode command.
